Add model cards for val_holdout (batch 5, final)

val_holdout/model_idx_4450/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4450
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | Chihuahua (n02085620) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 75 |
+| N Training Samples | 5 |

val_holdout/model_idx_4451/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4451
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | dhole (n02115913) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 48 |
+| N Training Samples | 10 |

val_holdout/model_idx_4452/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4452
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | jaguar (n02128925) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 90 |
+| N Training Samples | 10 |

val_holdout/model_idx_4453/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4453
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | weasel (n02441942) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 12 |
+| N Training Samples | 5 |

val_holdout/model_idx_4454/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4454
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | capuchin (n02492035) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 59 |
+| N Training Samples | 10 |

val_holdout/model_idx_4455/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4455
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | dhole (n02115913) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 24 |
+| N Training Samples | 8 |

val_holdout/model_idx_4456/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4456
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Leonberg (n02111129) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 39 |
+| N Training Samples | 8 |

val_holdout/model_idx_4457/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4457
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | groenendael (n02105056) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 73 |
+| N Training Samples | 7 |

val_holdout/model_idx_4458/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4458
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | wire-haired_fox_terrier (n02095314) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 72 |
+| N Training Samples | 8 |

val_holdout/model_idx_4459/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4459
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Chihuahua (n02085620) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 79 |
+| N Training Samples | 6 |

val_holdout/model_idx_4460/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4460
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | African_elephant (n02504458) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 99 |
+| N Training Samples | 6 |

val_holdout/model_idx_4461/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4461
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Pembroke (n02113023) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 46 |
+| N Training Samples | 6 |

val_holdout/model_idx_4462/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4462
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Rottweiler (n02106550) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 43 |
+| N Training Samples | 8 |

val_holdout/model_idx_4463/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4463
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | dugong (n02074367) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 99 |
+| N Training Samples | 9 |

val_holdout/model_idx_4464/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4464
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | groenendael (n02105056) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 40 |
+| N Training Samples | 9 |

val_holdout/model_idx_4465/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4465
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | boxer (n02108089) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 44 |
+| N Training Samples | 8 |

val_holdout/model_idx_4466/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4466
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | dugong (n02074367) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 58 |
+| N Training Samples | 9 |

val_holdout/model_idx_4467/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4467
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | Chihuahua (n02085620) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 29 |
+| N Training Samples | 10 |

val_holdout/model_idx_4468/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4468
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | Pekinese (n02086079) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 6 |
+| N Training Samples | 8 |

val_holdout/model_idx_4469/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4469
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Chihuahua (n02085620) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 19 |
+| N Training Samples | 6 |

val_holdout/model_idx_4470/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4470
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | wire-haired_fox_terrier (n02095314) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 8 |
+| N Training Samples | 10 |

val_holdout/model_idx_4471/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4471
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | Persian_cat (n02123394) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 74 |
+| N Training Samples | 6 |

val_holdout/model_idx_4472/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4472
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | groenendael (n02105056) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 66 |
+| N Training Samples | 5 |

val_holdout/model_idx_4473/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4473
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | coyote (n02114855) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 26 |
+| N Training Samples | 7 |

val_holdout/model_idx_4474/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4474
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | African_elephant (n02504458) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 34 |
+| N Training Samples | 9 |

val_holdout/model_idx_4475/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4475
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | chow (n02112137) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 65 |
+| N Training Samples | 5 |

val_holdout/model_idx_4476/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4476
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | Sussex_spaniel (n02102480) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 57 |
+| N Training Samples | 5 |

val_holdout/model_idx_4477/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4477
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | coyote (n02114855) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 88 |
+| N Training Samples | 8 |

val_holdout/model_idx_4478/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4478
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Pekinese (n02086079) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 4 |
+| N Training Samples | 8 |

val_holdout/model_idx_4479/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4479
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | papillon (n02086910) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 16 |
+| N Training Samples | 8 |

val_holdout/model_idx_4480/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4480
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | dugong (n02074367) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 67 |
+| N Training Samples | 5 |

val_holdout/model_idx_4481/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4481
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | papillon (n02086910) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 45 |
+| N Training Samples | 9 |

val_holdout/model_idx_4482/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4482
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | wire-haired_fox_terrier (n02095314) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 35 |
+| N Training Samples | 9 |

val_holdout/model_idx_4483/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4483
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | hyena (n02117135) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 6 |
+| N Training Samples | 7 |

val_holdout/model_idx_4484/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4484
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Pekinese (n02086079) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 37 |
+| N Training Samples | 9 |

val_holdout/model_idx_4485/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4485
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | wire-haired_fox_terrier (n02095314) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 57 |
+| N Training Samples | 5 |

val_holdout/model_idx_4486/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4486
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | silky_terrier (n02097658) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 92 |
+| N Training Samples | 5 |

val_holdout/model_idx_4487/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4487
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | chow (n02112137) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 86 |
+| N Training Samples | 6 |

val_holdout/model_idx_4488/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4488
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Pekinese (n02086079) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 92 |
+| N Training Samples | 8 |

val_holdout/model_idx_4489/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4489
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | impala (n02422699) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 73 |
+| N Training Samples | 9 |

val_holdout/model_idx_4490/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4490
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Pekinese (n02086079) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 50 |
+| N Training Samples | 8 |

val_holdout/model_idx_4491/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4491
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | Pekinese (n02086079) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 9 |
+| N Training Samples | 9 |

val_holdout/model_idx_4492/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4492
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | groenendael (n02105056) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 0 |
+| N Training Samples | 5 |

val_holdout/model_idx_4493/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4493
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | impala (n02422699) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 27 |
+| N Training Samples | 7 |

val_holdout/model_idx_4494/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4494
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | African_elephant (n02504458) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 34 |
+| N Training Samples | 6 |

val_holdout/model_idx_4495/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4495
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | silky_terrier (n02097658) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 48 |
+| N Training Samples | 6 |

val_holdout/model_idx_4496/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4496
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | silky_terrier (n02097658) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 84 |
+| N Training Samples | 9 |

val_holdout/model_idx_4497/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4497
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | Pembroke (n02113023) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 83 |
+| N Training Samples | 5 |

val_holdout/model_idx_4498/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4498
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | hyena (n02117135) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 54 |
+| N Training Samples | 8 |